This is actually really cool.
These researchers have used machine learning techniques to generate a model for a virus they theorised could kill E. coli, then synthesised that virus, and found it did actually kill E. Coli.
Phages, viruses that infect bacteria, can and have saved lives. It's a new treatment that was pioneered in the last few years and if you get, for example, a bad enough staph infection, it's one of the only things that can save you. The difficulty is, each phage typically only infects a very specific species of bacteria. This if not a problem at all for bacteria like golden staph which are typically the same (or similar enough for the phages that infect them) everywhere in the world, but there are also a lot of hyper localised bacteria.
I've been involved in a research project that involved collecting bacteria from local communities to try and search them for phages that could be used to treat bacterial infections in those communities, there's a huge amount of medical research time and funding going towards discovering new phage, keeping useful ones in cold storage, and airlifting them out in medical emergencies.
If we can create and synthesise custom phages it will save thousands of lives every year.
